A discussion about various replication techniques widely-used in distributed databases and nosql products.

1. REPLICATION
IN THE WILD
Ensar Basri Kahveci

2. Hello! Ensar Basri Kahveci
Distributed Systems Engineer @ Hazelcast
website: basrikahveci.com
linkedin: basrikahveci
twitter & github: metanet

3. - Leading open source Java IMDG
- Distributed Java collections, JCache, HD store, …
- Distributed computations and messaging
- Embedded or client - server deployment
- Integration modules & cloud friendly
- Highly available, scalable, elastic

4. REPLICATION
- Putting a data set into
multiple nodes.
- Each replica has a full copy.
- A few reasons for replication:
- Performance
- Availability

5. REPLICATION + PARTITIONING
- Mostly used with
partitioning.
- Two partitions: P1, P2
- Two replicas for each
partition.

6. NOTHING FOR FREE!
- Very easy to do when the data is immutable.
- Two main difficulties:
- Handling updates,
- Handling failures.

7. The dangers of replIcatIon and a solutIon
- Gray et al. [1] classify replication models by 2
parameters:
- Where to make updates: primary copy or update
anywhere
- When to make updates: eagerly or lazily

8. WHERE: PRIMARY COPY
- There is a single replica
managing the updates.
- No conflicts and no
conflict-handling logic.
- Implies sticky availability.
- When primary fails, a new
primary is elected.

9. WHERE: UPDATE ANYWHERE
- Each replica can initiate a
transaction to make an update.
- Complex concurrency control.
- Deadlocks or conflicts are
possible.
- In practice, there is also
multi-leader.

10. WHEN: EAGER REPLICATION
- Synchronously updates all
replicas as part of one atomic
transaction.
- Strong consistency.
- Level of availability can
degrade on node failures.
- Consensus algorithms

11. WHEN: LAZY REPLICATION
- Updates each replica with a
separate transaction.
- Updates can execute quite fast.
- High availability.
- Data copies can diverge.

12. WHERE?
WHEN?
PRIMARY COPY UPDATE ANYWHERE
EAGER
2PC [24]
Multi Paxos [5]
etcd and Consul (RAFT) [6]
Zookeeper (Zab) [7]
Kafka
2PC [24]
Paxos [5]
Hazelcast Cluster State Change [12]
MySQL 5.7 Group Replication [23]
LAZY
Hazelcast
MongoDB
ElasticSearch
Redis
Kafka
Dynamo [4]
Cassandra
Riak
Hazelcast Active-Active WAN
Replication [22]

13. PRIMARY COPY + EAGER REPLICATION
- When the primary fails, secondaries are
guaranteed to be up to date.
- Majority approach in consensus algorithms.
- Expensive. Mostly used for storing metadata.
- In Kafka, in-sync-replica set [11] is maintained.

14. UPDATE ANYWHERE + EAGER REPLICATION
- Each replica can initiate a new transaction.
- Concurrent transactions can compete with
each other.
- Possibility of races and deadlocks.
- Hazelcast Cluster State Change [12]

15. PRIMARy COPY + LAZY REPLICATION
- Hazelcast, Redis, ElasticSearch, Kafka ...
- The primary copy can execute updates fast.
- Secondaries can fall behind the primary. It is
called replication lag.
- It can lead to data loss during leader failover, but
still no conflicts.
- Secondaries can be used for reads.

16. Hazelcast: PRIMARy COPY + LAZY REPLICATION
PRIMARY
COPY
strong consistency
on a stable cluster
sticky availability
LAZY
REPLICATION
high throughput replication log

17. UPDATE ANYWHERE + LAZY REPLICATION
- Dynamo-style [4] highly available databases.
- Tunable quorums.
- Concurrent updates are first-class citizens.
- Possibility of conflicts
- Avoiding, discarding, detecting & resolving conflicts
- Eventual convergence
- Write repair, read repair and anti-entropy

18. Tunable QUORUMS
- W + R > N
- W = 3, R = 1, N = 3
- W = 2, R = 1, N = 3
- If W or R are not met
- Sloppy quorums and
hinted handoff

19. CONCURRENT UPDATES
- Avoiding conflicts: CRDTs [2]
- Strong eventual consistency
- Riak Data Types [3]
- Discarding conflicts: Last write wins
- Physical timestamps in Cassandra [8], [9]
- Detecting conflicts: Vector clocks [10]
- Dynamo-style databases [4]

20. EVENTUAL CONVERGENCE
- Write repair
- Read repair
- Active Anti-entropy
- Merkle trees

21. WHERE?
WHEN?
PRIMARY COPY UPDATE ANYWHERE
EAGER
strong consistency
simple concurrency
slow
inflexible
strong consistency
complex concurrency
expensive
deadlocks
LAZY
fast
eventual consistency
simple concurrency
Inconsistency
flexible
high availability
eventual consistency
conflicts

22. Recap
- We apply replication to make distributed
systems performant, available and fault
tolerant.
- Various replication protocols are built based
on when and where to make updates.
- No silver bullet. It is a world of trade-offs.

23. - We are hiring!
- Senior Java Developer
http://stackoverflow.com/jobs/129435/senior-java-developer-hazelcast
- Solution Architect
http://stackoverflow.com/jobs/131938/solutions-architect-hazelcast

24. REFerences
[1] Gray, Jim, et al. "The dangers of replication and a solution." ACM SIGMOD Record 25.2 (1996): 173-182.
[2] Shapiro, Marc, et al. "Conflict-free replicated data types." Symposium on Self-Stabilizing Systems. Springer, Berlin, Heidelberg, 2011.
[3] http://docs.basho.com/riak/kv/2.2.0/learn/concepts/crdts/
[4] DeCandia, Giuseppe, et al. "Dynamo: amazon's highly available key-value store." ACM SIGOPS operating systems review 41.6 (2007): 205-220.
[5] Lamport, Leslie. "Paxos made simple." ACM Sigact News 32.4 (2001): 18-25.
[6] Ongaro, Diego, and John K. Ousterhout. "In Search of an Understandable Consensus Algorithm." USENIX Annual Technical Conference. 2014.
[7] Hunt, Patrick, et al. "ZooKeeper: Wait-free Coordination for Internet-scale Systems." USENIX annual technical conference. Vol. 8. 2010.
[8] http://www.datastax.com/dev/blog/why-cassandra-doesnt-need-vector-clocks
[9] https://aphyr.com/posts/299-the-trouble-with-timestamps
[10] Raynal, Michel, and Mukesh Singhal. "Logical time: Capturing causality in distributed systems." Computer 29.2 (1996): 49-56.
[11] http://kafka.apache.org/documentation.html#replication
[12] http://docs.hazelcast.org/docs/latest/manual/html-single/index.html#managing-cluster-and-member-states
[13] E. Brewer, "Towards Robust Distributed Systems," Proc. 19th Ann. ACM Symp. Principles of Distributed Computing (PODC 00), ACM, 2000, pp. 7-10
[14] https://codahale.com/you-cant-sacrifice-partition-tolerance/
[15] http://blog.nahurst.com/visual-guide-to-nosql-systems
[16] http://www.allthingsdistributed.com/2008/12/eventually_consistent.html
[17] https://www.somethingsimilar.com/2013/01/14/notes-on-distributed-systems-for-young-bloods/
[18] https://www.infoq.com/articles/cap-twelve-years-later-how-the-rules-have-changed
[19] Gilbert, Seth, and Nancy Lynch. "Brewer's conjecture and the feasibility of consistent, available, partition-tolerant web services." Acm Sigact News 33.2 (2002): 51-59.
[20] https://martin.kleppmann.com/2015/05/11/please-stop-calling-databases-cp-or-ap.html
[21] https://henryr.github.io/cap-faq/
[22] http://docs.hazelcast.org/docs/3.7/manual/html-single/index.html#wan-replication
[23] https://dev.mysql.com/doc/refman/5.7/en/group-replication.html
[24] Notes on data base operating systems, JN Gray - Operating Systems, 1978

25. THANKS!Any questions?